wehub-resource-sync🚀 AI Engineering Roadmap
A comprehensive guide to becoming an AI Engineer, starting from Python fundamentals to building production-ready AI applications.
📚 Table of Contents
- 1️⃣ Master Python
- 2️⃣ AI with Python
- 3️⃣ Maths for ML
- 4️⃣ Understanding LLMs
- 5️⃣ LLM Research
- 6️⃣ AI Agents
- 7️⃣ Applied AI
- 8️⃣ AI Protocols (MCP)
- 9️⃣ Project-based Learning
- 🔟 Books
1️⃣ Master Python
Strong coding fundamentals are important.
Start with Python, and Harvard's CS50p is the best place to learn it.
🔗 Harvard CS50's Introduction to Programming with Python
- Duration: 9 weeks
- Time Commitment: 3-9 hours per week
- Difficulty: Introductory
- Platform: edX
2️⃣ AI with Python
Next, learn how Python is used in AI.
This 4-hour course by Andrew Ng is a great starting point.
🔗 AI Python for Beginners - DeepLearning.AI
- Duration: 4 hours 15 minutes
- Instructor: Andrew Ng
- Lessons: 35 video lessons
- Code Examples: 27 code examples
3️⃣ Maths for ML
Fundamentals of Linear Algebra, Probability, and Statistics are important, especially in AI research.
These playlists by Khan Academy are the perfect place to learn it:
🔗 Essential Math Playlists:
4️⃣ Understanding LLMs
These three videos by 3Blue1Brown are the best visual explainers of LLMs and their internal workings.
🔗 Neural Networks Playlist - 3Blue1Brown
Key Topics:
- How LLMs work
- Transformers Deep-dive
- Attention in transformers
- How LLMs store facts
5️⃣ LLM Research
Now that you understand what LLMs are, it's time to learn how to build them yourself.
Neural Nets zero-to-hero by Andrej Karpathy is the greatest series to do so.
🔗 Neural Networks: Zero to Hero - Andrej Karpathy
- Videos: 10 videos
- Total Views: 2M+ views
- Focus: Building neural networks from scratch
6️⃣ AI Agents
Before even jumping into the Agents, you should first read Anthropic AI's guide on building effective agents.
"To build an agent, you don't need complex frameworks or libraries, but rather composable patterns."
🔗 Building Effective Agents - Anthropic
- Published: December 19, 2024
- Focus: Simple, composable patterns for LLM agents
- Industry Insights: Real-world implementation patterns
7️⃣ Applied AI
I don't recommend chasing frameworks, but I took this course on CrewAI when I started.
João Moura precisely teaches how to think of agents like humans working together in a clear and practical manner.
🔗 Multi AI Agent Systems with CrewAI - Coursera
- Duration: 2 hours 41 minutes
- Instructor: João Moura
- Lessons: 18 video lessons
- Code Examples: 7 code examples
8️⃣ AI Protocols (MCP)
Now that you understand what agents are, it's time to connect them to external tools, APIs, and databases.
This free hands-on guide on MCP has 10+ projects.
🔗 MCP: The Illustrated Guidebook
- Edition: 2025 Edition
- Status: FREE
- Projects: 10+ hands-on projects
- Focus: Model Context Protocol implementation
9️⃣ Project-based Learning
This GitHub repo contains 75+ projects on AI Engineering covering:
- LLMs and RAGs
- Real-world AI agent applications
- Examples to implement, adapt, and scale in your projects
What you'll find:
- In-depth tutorials on LLMs and RAGs
- Real-world AI agent applications
- Examples to implement, adapt, and scale in your projects
- Resources for all skill levels
🔟 Books
Every AI engineer building real-world applications should read this book.
Chip Huyen's book is one of the best on AI Engineering.
🔗 AI Engineering Book - GitHub
What you'll learn:
- Understand what AI engineering is and how it differs from traditional ML engineering
- Learn the process for developing an AI application
- Explore various model adaptation techniques
- Examine bottlenecks for latency and cost when serving foundation models
- Choose the right model, metrics, data, and developmental patterns
🎯 Learning Path Summary
- Foundation → Master Python programming
- AI Basics → Learn Python for AI applications
- Mathematics → Build strong math fundamentals
- Understanding → Grasp how LLMs work internally
- Research → Learn to build neural networks from scratch
- Agents → Understand effective agent design patterns
- Application → Build multi-agent systems
- Integration → Connect agents to external tools and APIs
- Practice → Work on real-world projects
- Mastery → Deep dive into production AI engineering
🤝 Contributing
Found this roadmap helpful? Star ⭐ this repository and share it with others!
Happy Learning! 🚀